CN109741826B - Anesthesia evaluation decision tree construction method and equipment - Google Patents
Anesthesia evaluation decision tree construction method and equipment Download PDFInfo
- Publication number
- CN109741826B CN109741826B CN201811524873.7A CN201811524873A CN109741826B CN 109741826 B CN109741826 B CN 109741826B CN 201811524873 A CN201811524873 A CN 201811524873A CN 109741826 B CN109741826 B CN 109741826B
- Authority
- CN
- China
- Prior art keywords
- anesthesia
- decision tree
- anesthesia evaluation
- evaluation decision
- node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 206010002091 Anaesthesia Diseases 0.000 title claims abstract description 203
- 230000037005 anaesthesia Effects 0.000 title claims abstract description 203
- 238000011156 evaluation Methods 0.000 title claims abstract description 180
- 238000003066 decision tree Methods 0.000 title claims abstract description 116
- 238000010276 construction Methods 0.000 title claims abstract description 11
- 238000000034 method Methods 0.000 claims abstract description 46
- 238000012549 training Methods 0.000 claims abstract description 45
- 238000012795 verification Methods 0.000 claims abstract description 27
- 238000013138 pruning Methods 0.000 claims abstract description 21
- 238000004891 communication Methods 0.000 claims description 8
- 238000009966 trimming Methods 0.000 claims 1
- 238000010200 validation analysis Methods 0.000 claims 1
- 238000012274 Preoperative evaluation Methods 0.000 abstract description 2
- 201000010099 disease Diseases 0.000 description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 6
- 238000005259 measurement Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 238000013479 data entry Methods 0.000 description 2
- 238000013499 data model Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 1
- 206010020751 Hypersensitivity Diseases 0.000 description 1
- 208000012902 Nervous system disease Diseases 0.000 description 1
- 208000026935 allergic disease Diseases 0.000 description 1
- 230000007815 allergy Effects 0.000 description 1
- 238000009530 blood pressure measurement Methods 0.000 description 1
- 238000002512 chemotherapy Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011157 data evaluation Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 208000010643 digestive system disease Diseases 0.000 description 1
- 230000035622 drinking Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 208000030172 endocrine system disease Diseases 0.000 description 1
- 239000008103 glucose Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000002503 metabolic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001959 radiotherapy Methods 0.000 description 1
- 208000023504 respiratory system disease Diseases 0.000 description 1
- 208000011865 skeletal system disease Diseases 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000014001 urinary system disease Diseases 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a method and equipment for constructing an anesthesia evaluation decision tree. Wherein the method comprises the following steps: acquiring a training sample of an anesthesia evaluation decision tree, and determining branch variables of the anesthesia evaluation decision tree according to the information gain rate of the training sample; obtaining a verification sample of the anesthesia evaluation decision tree, and performing post pruning on the branch variables according to the verification sample to obtain a final anesthesia evaluation decision tree; wherein the final anesthesia evaluation decision tree is used for outputting an anesthesia level output variable. According to the anesthesia evaluation decision tree construction method and equipment provided by the embodiment of the invention, the model training method is adopted, and the confidence interval method is combined to perform back pruning on the model, so that the anesthesia evaluation decision tree model for anesthesia condition evaluation can be obtained, the workload of preoperative anesthesia evaluation is reduced, and the efficiency of preoperative evaluation of anesthesia is further improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of medical big data, in particular to a method and equipment for constructing an anesthesia evaluation decision tree.
Background
At present, the phenomenon of personnel shortage commonly exists among anesthetists in China, the operation amount is 100 hospitals every day, the anesthesia outpatient service amount is necessarily more than 100 hospitals every day, and the working strength and pressure of outpatient anesthetists and the waiting and hospitalizing experience of operation patients are greatly challenged. In order to solve the problem, a plurality of solutions are adopted, the traditional solution is anesthesia assessment based on machine learning, all the solutions adopt partial vital signs to carry out ASA grading, the vital sign information of a patient is not fully known, the evaluation ASA grading error rate is high, and a perfect anesthesia plan is lacked. Therefore, in view of the problems in the prior art, a method for generating an evaluation result of patient data through an algorithm model is found, and a doctor can refer to the evaluation result and then propose a doctor's opinion on an unreasonable evaluation to further improve the evaluation accuracy of the algorithm model and the efficiency of anesthesia evaluation, which is an urgent technical problem in the art.
Disclosure of Invention
In view of the above problems in the prior art, embodiments of the present invention provide a method and an apparatus for constructing an anesthesia evaluation decision tree.
In a first aspect, an embodiment of the present invention provides a method for constructing an anesthesia evaluation decision tree, including: acquiring a training sample of an anesthesia evaluation decision tree, and determining a branch variable of the anesthesia evaluation decision tree according to an information gain rate of the training sample; obtaining a verification sample of the anesthesia evaluation decision tree, and performing post pruning on the branch variables according to the verification sample to obtain a final anesthesia evaluation decision tree; wherein the final anesthesia evaluation decision tree is used to output an anesthesia level output variable.
Further, the obtaining of the training sample of the anesthesia evaluation decision tree includes: and extracting 70% of the data in the big data of the anesthesia evaluation as a training sample of the anesthesia evaluation decision tree.
Further, the determining branch variables of the anesthesia evaluation decision tree according to the information gain rate of the training samples, and accordingly, the information gain rate of the training samples includes:
wherein, a is a life feature attribute; the Gain _ ratio is the information Gain rate of the training sample with the selected vital sign attribute a as the split attribute; d is a training sample of the anesthesia evaluation decision tree; gain is the information Gain of selecting the vital sign attribute a as the split attribute; IV is the information entropy of a; ent is the information entropy of D; d i Dividing D according to the vital sign attribute a to generate V branch nodes, wherein the ith branch node comprises all values a of D, wherein the value a of the ith branch node is i The number of training samples of the anesthesia evaluation decision tree; pk is the proportion of the kth sample in D; and y is the number of types of samples in D.
Further, the obtaining a verification sample of the anesthesia evaluation decision tree includes: 30% of the large anesthesia evaluation data are extracted as verification samples of the anesthesia evaluation decision tree.
Further, the post-pruning the branch variables according to the verification sample to obtain a final anesthesia evaluation decision tree, including: and adopting a confidence interval method, obtaining the anesthesia evaluation result error of a single node through a positive-Taiwan distribution table, obtaining the anesthesia evaluation result errors of all child nodes under the father node aiming at the father node of the single node, further obtaining the weighted values of the anesthesia evaluation result errors of all child nodes, and pruning and removing all child nodes under the father node if the weighted values are larger than the anesthesia evaluation result errors of the father node and the anesthesia evaluation result errors of the single node are the minimum values.
Further, the obtaining the error of the anesthesia evaluation result of the single node through the positive-token distribution table by using the confidence interval method comprises the following steps:
E r ＝B r /A r
wherein 1- α is the confidence level; a. the r Number of anesthesia assessments for a single node; b is r Is A r Number of false anesthesia assessments; e r Is the error rate; mu.s r Error of anesthesia evaluation for a single node, μ r Has a confidence interval of
Z α/2 Quantile in positive-Taiyang distribution; p is the probability distribution with a confidence level of 1-alpha.
Further, the further obtaining weighted values of the anesthesia evaluation result errors of all the child nodes comprises:
wherein,
weighting values of anesthesia evaluation result errors for all child nodes; i is the ith child node; k is the number of all child nodes; theta i The ratio of the ith child node occupied under the father node is obtained; mu.s i The error of the anesthesia evaluation result for the ith single node is taken and the minimum value is taken.
In a second aspect, an embodiment of the present invention provides an apparatus for constructing an anesthesia evaluation decision tree, including:
the branch variable determining module is used for acquiring a training sample of an anesthesia evaluation decision tree and determining a branch variable of the anesthesia evaluation decision tree according to the information gain rate of the training sample;
the anesthesia evaluation decision tree acquisition module is used for acquiring a verification sample of the anesthesia evaluation decision tree, and performing post pruning on the branch variables according to the verification sample to obtain a final anesthesia evaluation decision tree;
wherein the final anesthesia evaluation decision tree is used to output an anesthesia level output variable.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the anesthesia evaluation decision tree construction method provided by any of the various possible implementations of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform a method for constructing a anesthesia evaluation decision tree provided in any of various possible implementations of the first aspect.
According to the anesthesia evaluation decision tree construction method and equipment provided by the embodiment of the invention, the model training method is adopted, and the confidence interval method is combined to perform back pruning on the model, so that the anesthesia evaluation decision tree model for anesthesia condition evaluation can be obtained, the workload of preoperative anesthesia evaluation is reduced, and the efficiency of preoperative evaluation of anesthesia is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below to the drawings required for the description of the embodiments or the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart of a method for constructing an anesthesia evaluation decision tree according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a preoperative anesthesia evaluation system according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an apparatus for constructing an anesthesia evaluation decision tree according to an embodiment of the present invention;
fig. 4 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. In addition, technical features of various embodiments or individual embodiments provided by the invention can be arbitrarily combined with each other to form a feasible technical solution, but must be realized by a person skilled in the art, and when the technical solution combination is contradictory or cannot be realized, the technical solution combination is not considered to exist and is not within the protection scope of the present invention.
The embodiment of the invention provides a method for constructing an anesthesia evaluation decision tree, and referring to fig. 1, the method comprises the following steps:
101. acquiring a training sample of an anesthesia evaluation decision tree, and determining a branch variable of the anesthesia evaluation decision tree according to an information gain rate of the training sample;
102. and obtaining a verification sample of the anesthesia evaluation decision tree, and performing post pruning on the branch variables according to the verification sample to obtain the final anesthesia evaluation decision tree.
Wherein the final anesthesia evaluation decision tree is used to output an anesthesia level output variable. Specifically, the output variables of the final anesthesia evaluation decision tree are the output variables of the decision tree with the anesthesia grades of I, II, III, IV, V and VI diagnosis results.
On the basis of the above embodiments, the anesthesia evaluation decision tree structure provided in the embodiments of the present inventionThe method for establishing the training sample of the anesthesia evaluation decision tree comprises the following steps: and extracting 70% of the data in the big data of the anesthesia evaluation as a training sample of the anesthesia evaluation decision tree. Specifically, a vital sign attribute a is obtained from a training sample of an anesthesia evaluation decision tree, and a has V values { a 1 ,a 2 ,…,a v The feature matrix is shown in table 1:
TABLE 1
On the basis of the foregoing embodiment, in the anesthesia evaluation decision tree construction method provided in the embodiment of the present invention, the branch variables of the anesthesia evaluation decision tree are determined according to the information gain rate of the training sample, and accordingly, the information gain rate of the training sample includes:
wherein a is a life feature attribute; the Gain _ ratio is the information Gain rate of the training sample with the vital sign attribute a as the split attribute; d is a training sample of the anesthesia evaluation decision tree; gain is the information Gain of selecting the vital sign attribute a as the split attribute; IV is the information entropy of a; ent is the information entropy of D; d i For dividing D according to the vital sign attribute a, V branch nodes are generated, wherein the ith branchThe branch node contains all values a on a in D i The number of training samples of the anesthesia evaluation decision tree; pk is the proportion of the kth sample in D; and y is the number of types of samples in D.
On the basis of the above embodiment, the method for constructing an anesthesia evaluation decision tree provided in the embodiment of the present invention, where the obtaining of the verification sample of the anesthesia evaluation decision tree includes: 30% of the large anesthesia evaluation data are extracted as verification samples of the anesthesia evaluation decision tree.
On the basis of the above embodiment, the method for constructing an anesthesia evaluation decision tree provided in the embodiment of the present invention, where post-pruning is performed on the branch variables according to the verification sample to obtain a final anesthesia evaluation decision tree, includes: and adopting a confidence interval method, obtaining the anesthesia evaluation result error of a single node through a positive-Taiwan distribution table, obtaining the anesthesia evaluation result errors of all child nodes under the father node aiming at the father node of the single node, further obtaining the weighted values of the anesthesia evaluation result errors of all child nodes, and pruning and removing all child nodes under the father node if the weighted values are larger than the anesthesia evaluation result errors of the father node and the anesthesia evaluation result errors of the single node are the minimum values.
On the basis of the above embodiment, the method for constructing an anesthesia evaluation decision tree provided in the embodiment of the present invention, where a confidence interval method is adopted, and an error of an anesthesia evaluation result of a single node is obtained through a positive-phase distribution table, includes:
E r ＝B r /A r
wherein 1- α is the confidence level; a. the r Number of anesthesia assessments for a single node; b r Is A r Number of false anesthesia assessments; e r Is the error rate; mu.s r Error of anesthesia evaluation for a single node, μ r Is a confidence interval of
Z α/2 Quantile in positive-Taiyang distribution; p is the probability distribution with a confidence level of 1-alpha.
On the basis of the above embodiment, the method for constructing an anesthesia evaluation decision tree provided in the embodiment of the present invention, further obtaining weighted values of anesthesia evaluation result errors of all child nodes, includes:
wherein,
weighting values of anesthesia evaluation result errors of all child nodes; i is the ith child node; k is the number of all child nodes; theta.theta. i The ratio of the ith child node occupied under the father node is obtained; mu.s i The error of the anesthesia evaluation result for the ith single node is taken and the minimum value is taken.
As a preferred solution in each of the above embodiments, the anesthesia evaluation decision tree model is selected from the C4.5 decision tree models. The anesthesia evaluation decision tree of the embodiment of the present invention is used in an application scenario of pre-operative anesthesia effect evaluation, and the application will be described with reference to fig. 2. It should be noted that the following description is only for illustrating the practical application value of the technical solution of the present invention, and is not meant to limit the technical solution of the present invention. All technical solutions that are within the spirit of the present invention are within the scope of the present patent. Referring to fig. 2, fig. 2 includes: preoperative data entry system, physician guidance data collection, medical history data, height measurement, weight measurement, blood pressure measurement, breath hold in time measurement, blow out match measurement, blood glucose measurement, physician assistance in looking at throat, looking at defective teeth, allergy history, smoking history, drinking history, metabolic capacity, circulatory system disease history, respiratory system disease history, digestive system disease history, urinary system disease history, endocrine system disease history, nervous system disease history, psychiatric system disease history, blood system disease history, skeletal system disease history, radiation therapy disease history, chemotherapy disease history, surgical disease history, airway assessment, historical data model training, algorithm model (i.e., anesthesia assessment decision tree model), personal data assessment, sign data processing, model iteration, anesthesia assessment opinions, user and operation, patient data entry system, mobile device, ASA grading, anesthesia plan, doctor and operation, and doctor opinion feedback. As can be seen from FIG. 2, historical data is formed from physician-guided data acquisition and medical history data, and an algorithm model (i.e., an anesthesia evaluation decision tree model) is trained through historical data model training, resulting in a usable algorithm model. And then, the user inputs personal information into the patient data input system through operation, and after the physical sign data is processed, the personal information is input into the algorithm model to carry out personal data evaluation. After evaluation, an ASA rating is formed, anesthesia plan, and fed back to the mobile device. Doctors propose doctors 'opinions for ASA grading and anesthesia planning, and then the doctors' opinions are fed back to form a new anesthesia evaluation opinion, ASA grading and anesthesia planning. And the feedback opinions of the doctor are returned to the algorithm model (namely the anesthesia evaluation decision tree model) to retrain the algorithm model (namely the self-learning process of the anesthesia evaluation decision tree model), so that the anesthesia evaluation decision tree model with a more accurate evaluation result is obtained, and the method is used for making and evaluating the anesthesia plan of the patient by the next wheel. It should be noted that the algorithm model (i.e., the anesthesia evaluation decision tree model) is disposed in the cloud server.
According to the anesthesia evaluation decision tree construction method provided by the embodiment of the invention, the model training method is adopted, and the confidence interval method is combined to perform back pruning on the model, so that the anesthesia evaluation decision tree model for anesthesia condition evaluation can be obtained, the workload of preoperative anesthesia evaluation is reduced, and the efficiency of preoperative anesthesia evaluation is further improved.
The implementation basis of the various embodiments of the present invention is realized by programmed processing performed by a device having a processor function. Therefore, in engineering practice, the technical solutions and functions thereof of the embodiments of the present invention can be packaged into various modules. Based on this reality, on the basis of the above embodiments, embodiments of the present invention provide an anesthesia evaluation decision tree construction apparatus, which is used for executing the anesthesia evaluation decision tree construction method in the above method embodiments. Referring to fig. 3, the apparatus includes:
a branch variable determining module 301, configured to obtain a training sample of an anesthesia evaluation decision tree, and determine a branch variable of the anesthesia evaluation decision tree according to an information gain rate of the training sample;
an anesthesia evaluation decision tree acquisition module 302, configured to acquire a verification sample of an anesthesia evaluation decision tree, and perform post pruning on the branch variables according to the verification sample to obtain a final anesthesia evaluation decision tree;
wherein the final anesthesia evaluation decision tree is used to output an anesthesia level output variable.
According to the anesthesia evaluation decision tree construction device provided by the embodiment of the invention, the branch variable determination module and the anesthesia evaluation decision tree acquisition module are adopted, and the model is subjected to back branch subtraction by adopting a model training method and combining a confidence interval method, so that an anesthesia evaluation decision tree model for anesthesia condition evaluation can be obtained, the workload of preoperative anesthesia evaluation is reduced, and the efficiency of preoperative anesthesia evaluation is further improved.
The method of the embodiment of the invention is realized by depending on the electronic equipment, so that the related electronic equipment is necessarily introduced. To this end, an embodiment of the present invention provides an electronic apparatus, as shown in fig. 4, including: at least one processor (processor)401, a communication Interface (Communications Interface)404, at least one memory (memory)402 and a communication bus 403, wherein the at least one processor 401, the communication Interface 404 and the at least one memory 402 communicate with each other via the communication bus 403. The at least one processor 401 may call logic instructions in the at least one memory 402 to perform the following method: acquiring a training sample of an anesthesia evaluation decision tree, and determining a branch variable of the anesthesia evaluation decision tree according to an information gain rate of the training sample; obtaining a verification sample of the anesthesia evaluation decision tree, and performing post pruning on the branch variables according to the verification sample to obtain a final anesthesia evaluation decision tree; wherein the final anesthesia evaluation decision tree is used for outputting an anesthesia level output variable.
Furthermore, the logic instructions in the at least one memory 402 may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. Examples include: acquiring a training sample of an anesthesia evaluation decision tree, and determining a branch variable of the anesthesia evaluation decision tree according to an information gain rate of the training sample; obtaining a verification sample of the anesthesia evaluation decision tree, and performing post pruning on the branch variables according to the verification sample to obtain a final anesthesia evaluation decision tree; wherein the final anesthesia evaluation decision tree is used for outputting an anesthesia level output variable. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. A method for constructing an anesthesia evaluation decision tree is characterized by comprising the following steps:
acquiring a training sample of an anesthesia evaluation decision tree, and determining a branch variable of the anesthesia evaluation decision tree according to an information gain rate of the training sample;
obtaining a verification sample of the anesthesia evaluation decision tree, and performing post pruning on the branch variables according to the verification sample to obtain a final anesthesia evaluation decision tree;
wherein the final anesthesia evaluation decision tree is used for outputting an anesthesia level output variable;
and post-pruning the branch variables according to the verification sample to obtain a final anesthesia evaluation decision tree, wherein the post-pruning comprises the following steps: acquiring anesthesia evaluation result errors of a single node through a positive-false distribution table by adopting a confidence interval method, acquiring anesthesia evaluation result errors of all child nodes under the father node aiming at the father node of the single node, further acquiring weighted values of the anesthesia evaluation result errors of all child nodes, and trimming and removing all child nodes under the father node if the weighted values are greater than the anesthesia evaluation result errors of the father node and the anesthesia evaluation result errors of the single node are the minimum values;
the method for acquiring the error of the anesthesia evaluation result of a single node through the positive-Taiwan distribution table by adopting the confidence interval method comprises the following steps:
E r =B r /A r
wherein,
is a confidence level; a. the r Number of anesthesia assessments for a single node; b r Is A r Number of false anesthesia assessments; e r Is the error rate;
for the anesthesia evaluation result error of a single node,
has a confidence interval of
；
Quantile in positive-Taiyang distribution; p is a confidence level of
A probability distribution of (a);
the further acquiring weighted values of the anesthesia evaluation result errors of all the child nodes comprises:
wherein,
weighting values of anesthesia evaluation result errors of all child nodes; i is the ith child node; k is the number of all child nodes;
the ratio of the ith child node occupied under the father node is obtained;
the error of the anesthesia evaluation result of the ith single node is calculated, and the minimum value is taken.
2. The method of claim 1, wherein the obtaining training samples of the anesthesia evaluation decision tree comprises:
and extracting 70% of the data in the big data of the anesthesia evaluation as a training sample of the anesthesia evaluation decision tree.
3. The method as claimed in claim 1, wherein the determining branch variables of the anesthesia evaluation decision tree according to the information gain rate of the training samples comprises:
wherein, a is a life feature attribute; gain _ ratio (D, a) is the information Gain rate of the training sample that selects the vital sign attribute a as the split attribute; d is a training sample of the anesthesia evaluation decision tree; gain (D, a) is an information increment for selecting the vital sign attribute a as the splitting attributeBenefiting; IV (a) is the information entropy of a; ent (D) is the information entropy of D; d i Dividing D according to the vital sign attribute a to generate V branch nodes, wherein the ith branch node comprises all values a of D, wherein the value a of the ith branch node is i Number of training samples, Ent (D) of anesthesia evaluation decision Tree of i ) Is D i The entropy of the information of (1); p is a radical of k The ratio of the kth sample in the D is shown; and y is the number of the types of the samples in D.
4. The method of claim 1, wherein the obtaining validation samples of the anesthesia evaluation decision tree comprises:
30% of the large anesthesia evaluation data are extracted as verification samples of the anesthesia evaluation decision tree.
5. An anesthesia evaluation decision tree construction apparatus, comprising:
the branch variable determining module is used for acquiring a training sample of an anesthesia evaluation decision tree and determining a branch variable of the anesthesia evaluation decision tree according to the information gain rate of the training sample;
the anesthesia evaluation decision tree acquisition module is used for acquiring a verification sample of the anesthesia evaluation decision tree, and performing post pruning on the branch variables according to the verification sample to obtain a final anesthesia evaluation decision tree;
wherein the final anesthesia evaluation decision tree is used for outputting an anesthesia level output variable;
and post-pruning the branch variables according to the verification sample to obtain a final anesthesia evaluation decision tree, wherein the post-pruning comprises the following steps: acquiring anesthesia evaluation result errors of a single node through a positive-false distribution table by adopting a confidence interval method, acquiring anesthesia evaluation result errors of all child nodes under the father node aiming at a father node of the single node, further acquiring weighted values of the anesthesia evaluation result errors of all child nodes, and pruning and removing all child nodes under the father node if the weighted values are larger than the anesthesia evaluation result errors of the father node and the anesthesia evaluation result errors of the single node are the minimum values;
the method for acquiring the error of the anesthesia evaluation result of the single node through the positive space distribution table by adopting a confidence interval method comprises the following steps:
E r =B r /A r
wherein,
is a confidence level; a. the r Number of anesthesia assessments for a single node; b is r Is A r Number of false anesthesia assessments; e r Is the error rate;
for the anesthesia evaluation result error of a single node,
is a confidence interval of
；
Quantile in positive-Taiyang distribution; p is a confidence level of
A probability distribution of (a);
the further acquiring weighted values of the anesthesia evaluation result errors of all the child nodes comprises:
wherein,
weighting values of anesthesia evaluation result errors of all child nodes; i is the ith child node; k is the number of all child nodes;
the ratio of the ith child node occupied under the father node is obtained;
the error of the anesthesia evaluation result of the ith single node is calculated, and the minimum value is taken.
6. An electronic device, comprising:
at least one processor, at least one memory, a communication interface, and a bus; wherein,
the processor, the memory and the communication interface complete mutual communication through the bus;
the memory stores program instructions executable by the processor, the processor calling the program instructions to perform the method of any one of claims 1 to 4.
7. A non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811524873.7A CN109741826B (en) | 2018-12-13 | 2018-12-13 | Anesthesia evaluation decision tree construction method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811524873.7A CN109741826B (en) | 2018-12-13 | 2018-12-13 | Anesthesia evaluation decision tree construction method and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109741826A CN109741826A (en) | 2019-05-10 |
| CN109741826B true CN109741826B (en) | 2022-09-13 |
Family
ID=66358796
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811524873.7A Active CN109741826B (en) | 2018-12-13 | 2018-12-13 | Anesthesia evaluation decision tree construction method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109741826B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110378591A (en) * | 2019-07-11 | 2019-10-25 | 仲恺农业工程学院 | Decision tree-based crop breeding information determination system and method |
| CN111128324A (en) * | 2019-12-19 | 2020-05-08 | 上海医芯智能科技有限公司 | Preoperative visit and anesthesia evaluation information system software |
| CN113034264A (en) * | 2020-09-04 | 2021-06-25 | 深圳大学 | Method and device for establishing customer loss early warning model, terminal equipment and medium |
| TWI807223B (en) * | 2020-10-13 | 2023-07-01 | 奇美醫療財團法人奇美醫院 | System and program product for auxiliary assessment of surgical anesthesia risk as well as method for establishing and using the same |
| CN113488187B (en) * | 2021-08-03 | 2024-02-20 | 南通市第二人民医院 | Anesthesia accident case collecting and analyzing method and system |
| CN114639460A (en) * | 2022-05-16 | 2022-06-17 | 天津医科大学眼科医院 | Cycloplegic demand prediction and paralysis post-diopter refractive state prediction method |
| CN116312958B (en) * | 2023-05-24 | 2023-09-15 | 成都市龙泉驿区中医医院 | Anesthesia risk early warning system, emergency management system and method |
| CN118267195A (en) * | 2024-03-08 | 2024-07-02 | 国家康复辅具研究中心 | Artificial limb receiving cavity aided design method, system and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103432651A (en) * | 2012-12-31 | 2013-12-11 | 南京理工大学 | Closed-loop intelligent anesthesia control system |
| CN103432650A (en) * | 2012-12-31 | 2013-12-11 | 南京理工大学 | Automatic anesthesia control method based on Bayesian network |
| CN108288130A (en) * | 2018-03-05 | 2018-07-17 | 湖北省第三人民医院 | Clinical care Performance Evaluation System and method based on data mining analysis platform |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015079355A1 (en) * | 2013-11-26 | 2015-06-04 | Koninklijke Philips N.V. | Methods for estimating dosage of anesthetic agent and for determining depth of anesthesia |
| CA2940422A1 (en) * | 2014-02-24 | 2015-08-27 | Children's Hospital Medical Center | Methods and compositions for personalized pain management |
-
2018
- 2018-12-13 CN CN201811524873.7A patent/CN109741826B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103432651A (en) * | 2012-12-31 | 2013-12-11 | 南京理工大学 | Closed-loop intelligent anesthesia control system |
| CN103432650A (en) * | 2012-12-31 | 2013-12-11 | 南京理工大学 | Automatic anesthesia control method based on Bayesian network |
| CN108288130A (en) * | 2018-03-05 | 2018-07-17 | 湖北省第三人民医院 | Clinical care Performance Evaluation System and method based on data mining analysis platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109741826A (en) | 2019-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109741826B (en) | Anesthesia evaluation decision tree construction method and equipment | |
| CN105913846B (en) | voice registration realization method, device and system | |
| CN109785928A (en) | Diagnosis and treatment proposal recommending method, device and storage medium | |
| CN110111886A (en) | A kind of intelligent interrogation system and method based on XGBoost disease forecasting | |
| CN109859815A (en) | A kind of adjuvant drug decision-making technique and intelligent adjuvant drug system | |
| CN107767929A (en) | CRF filling method, device, electronic equipment and storage medium | |
| CN109243546B (en) | Method and device for establishing anticoagulant drug effect optimization model | |
| CN111785366B (en) | Patient treatment scheme determination method and device and computer equipment | |
| CN111048167A (en) | Hierarchical case structuring method and system | |
| CN107730484A (en) | A kind of abnormal rabat intelligent identification Method and system based on deep learning | |
| CN110874409A (en) | Disease grading prediction system, method, electronic device and readable storage medium | |
| CN111091884B (en) | Patient main index matching system and method of hospital information integration platform | |
| CN114913953B (en) | Medical entity relationship identification method and device, electronic equipment and storage medium | |
| CN109273097B (en) | Automatic generation method, device, equipment and storage medium for pharmaceutical indications | |
| CN109243620A (en) | Drug effect optimization method and device based on therapeutic drug monitoring | |
| CN109492107A (en) | A kind of method and device of hospital guide | |
| CN108877924A (en) | A kind of asthma method of determining probability and device | |
| CN111326243A (en) | Triage recommendation method and device, electronic equipment and storage medium | |
| CN110957013B (en) | Method and device for localization of clinical pathways based on genetic algorithm | |
| CN112071431B (en) | Clinical path automatic generation method and system based on deep learning and knowledge graph | |
| CN109559788A (en) | A kind of history-taking method and device | |
| CN109712715A (en) | A kind of scoring processing method and processing device of physiological data | |
| US20220199256A1 (en) | Search method and information processing system | |
| CN109545350A (en) | A kind of hospital guide's method and device | |
| CN115761024A (en) | Blood vessel mask image generation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |